© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12126
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names with multiple parts, including some indications it might be trying to extract politicians as well.

    oai_token-act-pair · gemini-2.0-flash

    Defaultib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.66
    je
    -0.47
     R
    -0.44
     S
    -0.44
    titution
    -0.43
    ate
    -0.43
    Koordinaten
    -0.43
    l
    -0.41
    <eos>
    -0.40
    ть
    -0.40
    POSITIVE LOGITS
     Theſe
    0.83
     ujednoznacz
    0.77
     المعيارى
    0.76
     Efq
    0.75
    AddTagHelper
    0.75
    expandindo
    0.73
     purpoſe
    0.72
     myſelf
    0.72
     ddelweddau
    0.71
     Monfieur
    0.71
    Activations Density 1.353%

    No Known Activations